All authors
Claude Skills by curiositech
github.com/curiositech1,260 skills8 installs1,712 views
- Dag Fast DecompositionBuild and validate a static DAG reachability index from source-qualified path/chain decompositions and partial transitive-edge filtering. NOT for treating a partial edge filter as a complete transitive reduction or runtime scheduler.Votes: 0GitHub stars: 2
- Dag OrchestratorThe intelligence layer of Jury-rig. Decomposes natural language tasks into proposed Hierarchical Task DAGs (HTDAGs), matches subtasks to skills, proposes wave and revision contracts, and expands nodes only when evidence supports a revised graph. Use for 'orchestrate', 'execute DAG', 'parallel agents', 'decompose task', 'coordinate skills'. NOT for single-skill tasks or simple linear workflows.Votes: 0GitHub stars: 2
- Dag Output ValidatorValidates agent outputs against expected schemas and quality criteria. Reports structural and content checks within the declared evidence scope. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).Votes: 0GitHub stars: 2
- Dag Semantic MatcherMatches natural language task descriptions to appropriate skills using semantic similarity. Handles fuzzy matching, intent extraction, and capability alignment. Activate on 'find skill', 'match task', 'semantic search', 'skill lookup', 'what skill for'. NOT for ranking matches (use dag-capability-ranker) or skill catalog (use dag-skill-registry).Votes: 0GitHub stars: 2
- Dag Visual Editor DesignDesign modern, intuitive DAG/workflow visual editors that feel like LEGO, not LabView NOT for runtime DAG admission, graph execution, or claiming usability without user testing.Votes: 0GitHub stars: 2
- Dark Mode Design ExpertDesign accessible dark-mode interfaces with contrast, elevation, system-preference, and cross-device readability guidance.Votes: 0GitHub stars: 2
- Db Retention And CompactionDesigns and audits data retention and file compaction for an embedded SQLite datastore in a long-lived service — a unified retention registry (one declared policy per table), TTL / absolute-age / row-count-cap policies, a fail-loud coverage guard, WAL/checkpoint tuning, and auto_vacuum/incremental-vacuum so pruning actually shrinks the file. Use when a SQLite DB grows unbounded, a table has an index but no DELETE, a pruned DB never shrinks on disk, metrics are stored as raw events forever, or...Votes: 0GitHub stars: 2
- Decision Models From The FieldApply recognition-primed decision making to agents operating under time pressure, uncertainty, and ambiguous cues. Use for situation assessment, RPD-style action selection, and decision-support design in operational settings. NOT for batch optimization, static planning with full information, or tasks where exhaustive search is cheap and harmless.Votes: 0GitHub stars: 2
- Decker Lesser 1995 Gpgp TaemsApply GPGP/TAEMS coordination as local-scheduler constraints under explicit task, view, commitment, and delivery assumptions. NOT for assuming global task visibility, reliable delivery, or modern execution authority.Votes: 0GitHub stars: 2
- Derived Index Consent BoundaryAudit or design server-side indexes, directories, reputations, or aggregates that are DERIVED from traffic a platform witnesses (chain heads, run verdicts, heartbeats, publish activity) so that consent gates the derivation, not merely the read: no shadow index over non-consenting principals, post-consent-only evidence windows, retention bounds and delete-propagation into derived rows, activity-oracle threat modeling, and audit-logged ranking discretion. Use when building a capability director...Votes: 0GitHub stars: 2
- Design Consistency AuditorAudit and maintain design system consistency, UX/UI patterns, color palettes, and design best practices across frontend applicationsVotes: 0GitHub stars: 2
- Destructive Action Policy MatrixClassify every destructive/gated action an agent body can attempt (git, filesystem, network, shell, github) into block/approve/allow tiers, and audit whether the pre-tool and post-tool governance backing that classification is real: blocked actions proven zero-side-effect by a negative fixture, every denial backed by a receipt and a transcript event, every block-tier denial paired with a safe alternative, and no unmanaged or same-UID body ever marked "contained." Use when building or reviewin...Votes: 0GitHub stars: 2
- Developer Surface StrategistChooses and designs developer surfaces for an agentic product: SDK, CLI, MCP, GUI, API, webhooks, and pd tube-style listener/sender workflows. Use when deciding why a user belongs in an SDK versus CLI/MCP/GUI, planning Python SDK parity, or making agent invocation easy across languages. NOT for implementing the full SDK, generic API docs, or UI visual design.Votes: 0GitHub stars: 2
- Discourse CoordinatorMeta-skill that orchestrates the discourse skill suite: routes between steel-man-argument, socratic-questioning, toulmin-argument-analysis, logical-fallacy-detector, bad-faith-rhetoric-detector, discourse-elision-analyzer, forensic-speech-structure, and productive-discourse-facilitator. Use when analyzing conversations, facilitating discourse, or operating as a dialogue copilot. Maintains mode (silent analysis, coaching overlay, active facilitator) and decides which skills to invoke based on ...Votes: 0GitHub stars: 2
- Distributed AlgorithmsFoundational distributed computing algorithms for consensus, coordination, and fault toleranceVotes: 0GitHub stars: 2
- Distributed Tracing W3c ContextImplementing distributed tracing with W3C Trace Context — the byte-precise `traceparent` and `tracestate` header formats, OpenTelemetry's W3CTraceContextPropagator as the modern default (replacing X-B3-* and X-Datadog-*), head vs tail sampling, and HTTP→SQL trace propagation via sqlcommenter. Grounded in the W3C REC and OpenTelemetry specs. NOT for OTel metrics/logs pipelines, vendor backend setup (Datadog/Honeycomb/Jaeger/Tempo), or browser RUM tracing.Votes: 0GitHub stars: 2
- Dockerfile Build Cache MasteryUse when optimizing Docker builds with BuildKit, designing multi-stage Dockerfiles, leveraging cache mounts, building multi-arch images, choosing distroless vs alpine, or signing images with cosign. Triggers: docker build slow, layer cache not hitting, npm install / pip install reruns, multi-stage final image bloat, glibc vs musl issues, RUN --mount=type=cache, BUILDKIT_INLINE_CACHE, registry cache exporters, qemu emulation for arm64, COPY ordering for cache. NOT for Docker daemon admin, Kube...Votes: 0GitHub stars: 2
- Drydock Program ArchitectureDesigns, reconciles, and reviews an end-to-end Drydock program for safely staging agent runtimes: immutable worktree provenance, disposable VM containment, typed effect brokerage, global body accounting, resurrection, subscription-capacity economics, context compaction, operator control, evidence, and promotion. Use when several Drydock contracts must compose into one architecture, implementation hypertree, diagram set, or release plan. NOT for launching Port Daddy, running an untrusted subje...Votes: 0GitHub stars: 2
- Duckdb AnalyticsUse when running analytical SQL over Parquet/CSV/JSON without a warehouse, replacing pandas for data wrangling, joining S3 data in-place, building local data marts, or embedding OLAP into an app. Triggers: read_parquet/read_csv setup, partitioned dataset queries, hive partitioning, glob patterns for S3, COPY TO export, attach Postgres/MySQL, UDFs in Python/R, MotherDuck cloud sync, columnar performance vs row stores. NOT for OLTP workloads (concurrent writes), distributed analytics at petabyt...Votes: 0GitHub stars: 2
- Embedded AgencyDecision-theoretic framework for agents embedded within the environments they model and act uponVotes: 0GitHub stars: 2
- Empirical Systems EvaluationRigorous benchmarking of multi-agent coordination systems: experiment design, statistical analysis, human evaluation protocols, and reproducible reporting. NOT FOR ML model evaluation (use llm-evaluation-harness), A/B testing for web products, survey design, or general data science.Votes: 0GitHub stars: 2
- Episodic Memory AlgorithmsData structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory"...Votes: 0GitHub stars: 2
- Epistemic Coverage ScanAn innate exploratory drive that guarantees no graph node remains permanently invisible to an agent population. After a warm-up period (step > 3), each agent fires a coverage scan with probability |unseen_nodes| / |all_nodes|. When triggered, the agent teleports directly to the globally unseen node with the highest belief uncertainty, works it, and returns control to the normal action-selection loop. Probability is self-annealing: it starts near 1.0 when almost everything is unseen and decays...Votes: 0GitHub stars: 2
- Evaluating Rapport Based ApproachApply rapport-based elicitation to resistant or semi-cooperative humans and agents. Use when coercive prompting or brittle handoffs damage cooperation. NOT for routine cooperative tasks, pure technical debugging, or already reliable exchanges.Votes: 0GitHub stars: 2
- Expected Free Energy Action SelectionPrincipled action selection for autonomous agents using Expected Free Energy (EFE) under the Active Inference framework. Each candidate action is scored as G(n) = w_prag * (-E[p_n] * damping) + w_epist * (-Var[p_n] * novelty(n)), where agent beliefs are maintained as per-node Beta distributions and updated via Bayesian observation. Selection is a softmax over -gamma * G, making exploration an automatic consequence of uncertainty rather than a hardcoded epsilon. Precision weights w_prag and w_...Votes: 0GitHub stars: 2
- Expert Task AnalysisAnalytical methods for decomposing expert performance into cognitive and physical task componentsVotes: 0GitHub stars: 2
- Expungement Site OperationsOperationalizing an expungement website — user intake flows, document generation pipelines, court filing integrations, payment processing, state-by-state workflow variations, customer support for sensitive populations, and the handoff between automated systems and human legal review. Activate on 'expungement operations', 'legal tech SaaS', 'court filing integration', 'document automation pipeline', 'expungement business', 'legal service workflow', 'multi-state legal operations'. NOT for expun...Votes: 0GitHub stars: 2
- Falsification FirstRefute-before-prove research discipline: automated counterexample sweeps before any formalization, meter-integrity audits for information-bound experiments, mutation-tested model checkers, pre-registered commit-or-cut gates for speculative directions, wrong-turn reporting, and numeric-claim provenance. Use when validating any new theorem, bound, equilibrium, or security claim; when building or trusting a checker, simulator, or experiment; or when deciding whether a speculative research direct...Votes: 0GitHub stars: 2
- Fast And Practical Dag Decomposition PaperApply practical DAG decomposition, transitive-edge reduction, and reachability indexing to dense dependency graphs. Use when low width and repeated queries justify preprocessing. NOT for cyclic graphs, one-off graph checks, or exact-minimum-chain requirements.Votes: 0GitHub stars: 2
- Fast And Practical Dag Decomposition WitApply practical DAG decomposition, transitive-edge reduction, and reachability indexing to dense dependency graphs. Use when low width and repeated queries justify preprocessing. NOT for cyclic graphs, one-off graph checks, or exact-minimum-chain requirements.Votes: 0GitHub stars: 2
- Feature Flag Rollout StrategistUse when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 ...Votes: 0GitHub stars: 2
- Federated Harbor AuthorDrafting and iterating sections of The Federated Harbor whitepaper — the third paper in the Curiositech sequence after Anchor (local identity) and Bonded Commons (local coordination), extending coordination across machines and administrative domains. Use when authoring a section, rewriting a section after a redteam/whitehat round, or composing a new chapter. NOT for marketing copy, NOT for the other two papers, NOT for production threat response.Votes: 0GitHub stars: 2
- Federated Harbor RedteamAdversarial reviewer for The Federated Harbor whitepaper — the third paper in the Curiositech sequence after Anchor and Bonded Commons. Probes federation-specific threats: trust transitivity, cross-harbor token forgery, federated revocation under partition, cross-harbor Sybil, cross-domain settlement, equivocation, bond-pool draining, cold-start joining, federation-operator Sybil. Use during a versioned red-vs-white round; pairs with federated-harbor-whitehat. NOT for incident response, NOT f...Votes: 0GitHub stars: 2
- Federated Harbor WhitehatDefensive counterpart to federated-harbor-redteam: closes the smells that red team opens against The Federated Harbor whitepaper. Federation-specific defenses for cross-harbor primitives — mechanization commitments, scope hedges, cross-paper dependency formalization, pre-emptive analogies (CT, Macaroons, atomic swaps), and defense-in-depth framing (refuses vs prices). Use during a versioned red-vs-white round; pairs with federated-harbor-redteam. NOT for ad-hoc code review, NOT for the Anchor...Votes: 0GitHub stars: 2
- Find SkillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.Votes: 0GitHub stars: 2
- Fipa 00023 Agent ManagementFIPA standard for agent platform management including lifecycle, directory, and communication servicesVotes: 0GitHub stars: 2
- Fipa 00025 Interaction Protocol LibraryFIPA standard library of agent interaction protocols for structured multi-agent communicationVotes: 0GitHub stars: 2
- Fipa 00037 Communicative Act LibraryInterpret and design bounded FIPA communicative-act exchanges using XC00037H semantics while keeping delivery, authority, and external effects separate. NOT for proving delivery, task authorization, or external effect completion.Votes: 0GitHub stars: 2
- Fipa 00086 Ontology ServicePlan and diagnose FIPA-style ontology-service interactions while keeping declared ontology relations, provider capability, and application authorization separate. NOT for treating an ontology mapping as provider authority or guaranteed interoperability.Votes: 0GitHub stars: 2
- Fischer Lynch Paterson 1985 Flp ImpossibilityFoundational impossibility result proving consensus cannot be guaranteed in asynchronous systems with even one faulty processVotes: 0GitHub stars: 2
- Fleet Event Spawn TrustSecure the path from an inbound event (webhook, email, SMS, GitHub comment, file, cron) to an agent spawn in the Port Daddy fleet. Use when wiring trigger sources to agents, reviewing the io-wiring registry, adding a trust/permission gate, hardening output sinks (SSRF/path traversal), scoping tools by provenance, or proving the spawn path is safe against prompt-injection → tool-abuse. Encodes ADR-0093 and the red-team threat model. NOT for generic Coast Guard sandboxing (ADR-0050), the macaro...Votes: 0GitHub stars: 2
- Focus Receipt Proof GateAudit whether a "current product focus receipt" (Decision/Now/Why-now/Evidence/Not-now/Cut-suspend/First-visible-proof/ Acceptance-gate/Kill-revisit-trigger/Owner/Review-date) and the work order it gates state a real, testable decision and a real agent launch — not planning-placeholder prose that sounds like an assignment but can't be proven. Use when deciding whether to launch an agent chain against a milestone or a stated "focus," when a work order lacks explicit input/output/owner/proof-ga...Votes: 0GitHub stars: 2
- Frame0 WireframingBuild low-fidelity wireframes, screen mockups, and user-flow diagrams in Frame0 (the hand-drawn Balsamiq-style wireframing tool) through its connected MCP server. Use when asked to wireframe a screen, sketch a UI, make a low-fi mockup, lay out an app's screens, or diagram a user flow with clickable links. Triggers: "wireframe", "frame0", "low-fi mockup", "sketch a screen", "user flow", "lo-fi", "rough out the UI". NOT for high-fidelity visual design, brand systems, or color/typography polish ...Votes: 0GitHub stars: 2
- Game Theoretic Agent IncentivesAudit strategic incentives in repeated multi-agent coordination, especially advisory claims, observable deviations, punishment, and collusion. Use when agents can gain by ignoring a coordination protocol. NOT for payment/auction mechanism design (nisan-et-al-2007-algorithmic-game-theory), aligned agents, or implementation of file claims and locks.Votes: 0GitHub stars: 2
- Generative Music AudioGenerate music, sound effects, voice/TTS, and full songs across hosted APIs (Suno, Udio, ElevenLabs Music, Lyria, Cartesia, Hume) and open-weights models (ACE-Step, MusicGen, Stable Audio, YuE, DiffRhythm, Chatterbox, F5-TTS). Activate on: AI music, generate song, text to music, MusicGen, Suno, Udio, Stable Audio, ElevenLabs music, voice clone, TTS, sound effects, foley, mastering, stem separation, lip-sync audio. NOT for: voice in finished video (use generative-video-2026 lip-sync), audio po...Votes: 0GitHub stars: 2
- Generative Video 2026Pick, prompt, and pipeline frontier video generation models — Sora 2, Veo 3.1, Kling 3, Runway Gen-4 + Aleph + Act-Two, Seedance 2.0, Hailuo, Luma, Pika, PixVerse — plus open weights (Wan 2.2, HunyuanVideo-1.5, LTX-2.3, Mochi, CogVideoX), lip-sync (Hedra, Sync.so, LatentSync), and video-to-video editing. Activate on: AI video, text to video, image to video, video to video, Sora API, Veo API, Kling, Runway Aleph, Wan 2.2, HunyuanVideo, LTX video, lip-sync video, talking head, character consist...Votes: 0GitHub stars: 2
- Giant Squid HooksReference for the Giant Squid Harness hook tentacles (bin/pd-hook-prompt, bin/pd-hook-pre-tool, bin/pd-hook-post-tool, bin/pd-hook-stop) — the per-vendor event contracts, dial resolution, output channels, loop guards, and test seams that govern how Port Daddy rides inside Claude Code, Gemini CLI, Codex CLI, and Antigravity lifecycles. Use when editing a tentacle, wiring a new hook event, debugging a hook that fired wrong (or not at all), or verifying vendor block contracts. NOT for operating ...Votes: 0GitHub stars: 2
- Git Best PracticesExpert in Git workflows, conventions, and patterns for modern development teams and AI agents. Activate on: branching strategy, commit conventions, git hooks, pre-commit, husky, lint-staged, trunk-based development, git worktree, monorepo git, PR review workflow, conventional commits, git workflow. NOT for: CI/CD pipelines (use github-actions-pipeline-builder), repository hosting (use devops-automator), multi-agent orchestration (use multi-agent-coordination).Votes: 0GitHub stars: 2
- Github Actions Matrix PatternsUse when designing matrix builds (OS x version x dimension), composing reusable workflows, gating jobs on conditions, doing OIDC to AWS/GCP/Cloudflare without long-lived secrets, sharding tests across runners, or fixing cache invalidation. Triggers: workflow_call between repos, fail-fast: false tradeoffs, exclude/include matrix surgery, environment protection rules, OIDC trust policy setup, concurrency cancellation on duplicate pushes, artifact reuse across jobs, conditional job matrices comp...Votes: 0GitHub stars: 2
- Github App ActuatorPublish branches, pull requests, comments, review replies, readiness changes, reviewer requests, and merge-queue actions through Port Daddy's attributable GitHub App actuator without exposing or falling back to an operator's personal GitHub credentials. Use before any GitHub mutation, when a PR would otherwise appear as the human operator, when retiring ambient gh authentication, or when diagnosing a missing Fleetbot publication capability. NOT for read-only GitHub inspection unless repositor...Votes: 0GitHub stars: 2